Update to Power BI Desktop

{
  "name": "powerbi-revenue-digital-twin",
  "description": "Use when designing or running a Power BI revenue digital twin for sales forecasting, target-gap simulation, backlog-to-invoice scenarios, what-if revenue paths, budget attainment, and forecast-to-cash decision support from an open Power BI Desktop model or exported forecast CSVs.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 138
    }
  ],
  "skill_md_contents": "---\r\nname: powerbi-revenue-digital-twin\r\ndescription: Use when designing or running a Power BI revenue digital twin for sales forecasting, target-gap simulation, backlog-to-invoice scenarios, what-if revenue paths, budget attainment, and forecast-to-cash decision support from an open Power BI Desktop model or exported forecast CSVs.\r\n---\r\n\r\n# Power BI Revenue Digital Twin\r\n\r\nUse this skill when the user wants to move beyond a static sales forecast into scenario simulation: \"How do we still hit budget?\", \"What if delivery slips?\", \"Which backlog must convert?\", or \"Which customers/products close the revenue gap?\"\r\n\r\n## Workflow\r\n\r\n1. Start read-only. Use the open Desktop model through `Invoke-PowerBIAIForecast.ps1` or existing forecast CSVs. Do not write to PBIX/PBIP unless explicitly requested.\r\n2. Establish the current target gap by month: AI forecast, roll forecast, budget, actual-to-date, open backlog, expected backlog revenue.\r\n3. Build scenario levers:\r\n   - backlog acceleration or delay\r\n   - conversion probability changes\r\n   - customer/product demand uplift or erosion\r\n   - working-day and holiday impact\r\n   - budget or roll target constraint\r\n   - supply or delivery risk\r\n4. Produce at least three scenarios:\r\n   - base case from the current AI forecast\r\n   - target case showing what must change to hit budget or roll\r\n   - risk case showing likely downside if weak backlog or volatile segments slip\r\n5. Rank the smallest set of customer/product/month changes that explain or close the gap.\r\n\r\n## Required outputs\r\n\r\n- `forecast_month`\r\n- `target_metric` such as Budget or Roll\r\n- `current_ai_forecast`\r\n- `target_gap`\r\n- `required_backlog_conversion`\r\n- `required_residual_demand`\r\n- `top_gap_drivers`\r\n- `scenario_name`\r\n- `scenario_forecast`\r\n- `scenario_probability`\r\n- `explanation`\r\n\r\n## Quality gates\r\n\r\n- Mark a scenario `not_actionable` when it depends on segments already flagged `advisory_only`, `biased`, or `sparse` without human validation.\r\n- Separate controllable levers from non-controllable statistical demand.\r\n- Never present a single scenario as truth; show assumptions and sensitivity.\r\n"
}